# (ASNA) An Attention-based Siamese-Difference Neural Network with Surrogate Ranking Loss function for Perceptual Image Quality Assessment

arXiv: https://arxiv.org/abs/2105.02531 · HTML: https://mlsanity.com/paper/2105.02531/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 16 of its 44 references that are in the map.
- First posted on arXiv 6 May 2021.

## Builds on (most cited first, 16 of 16)

- [The Unreasonable Effectiveness of Deep Features as a Perceptual Metric](https://mlsanity.com/paper/1801.03924/) (2018)
- [Batch Normalization: Accelerating Deep Network Training by Reducing Internal Covariate Shift](https://mlsanity.com/paper/1502.03167/) (2015)
- [Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localization](https://mlsanity.com/paper/1610.02391/) (2016)
- [Photo-Realistic Single Image Super-Resolution Using a Generative Adversarial Network](https://mlsanity.com/paper/1609.04802/) (2016)
- [Enhanced Deep Residual Networks for Single Image Super-Resolution](https://mlsanity.com/paper/1707.02921/) (2017)
- [Convolutional LSTM Network: A Machine Learning Approach for Precipitation Nowcasting](https://mlsanity.com/paper/1506.04214/) (2015)
- [Image Super-Resolution Using Deep Convolutional Networks](https://mlsanity.com/paper/1501.00092/) (2014)
- [The Perception-Distortion Tradeoff](https://mlsanity.com/paper/1711.06077/) (2017)
- [Fully Convolutional Siamese Networks for Change Detection](https://mlsanity.com/paper/1810.08462/) (2018)
- [Deep Neural Networks for No-Reference and Full-Reference Image Quality Assessment](https://mlsanity.com/paper/1612.01697/) (2016)
- [PIPAL: a Large-Scale Image Quality Assessment Dataset for Perceptual Image Restoration](https://mlsanity.com/paper/2007.12142/) (2020)
- [PieAPP: Perceptual Image-Error Assessment through Pairwise Preference](https://mlsanity.com/paper/1806.02067/) (2018)
- [Learning a No-Reference Quality Metric for Single-Image Super-Resolution](https://mlsanity.com/paper/1612.05890/) (2016)
- [Deep Visual Attention Prediction](https://mlsanity.com/paper/1705.02544/) (2017)
- [SoDeep: a Sorting Deep net to learn ranking loss surrogates](https://mlsanity.com/paper/1904.04272/) (2019)
- [Image Quality Assessment for Perceptual Image Restoration: A New Dataset, Benchmark and Metric](https://mlsanity.com/paper/2011.15002/) (2020)

## Built on by (most cited first, 7 of 7)

- [NTIRE 2022 Challenge on Perceptual Image Quality Assessment](https://mlsanity.com/paper/2206.11695/) (2022)
- [Multi-stage image denoising with the wavelet transform](https://mlsanity.com/paper/2209.12394/) (2022)
- [Incorporating Semi-Supervised and Positive-Unlabeled Learning for Boosting Full Reference Image Quality Assessment](https://mlsanity.com/paper/2204.08763/) (2022)
- [Conformer and Blind Noisy Students for Improved Image Quality Assessment](https://mlsanity.com/paper/2204.12819/) (2022)
- [Image Quality Assessment with Gradient Siamese Network](https://mlsanity.com/paper/2208.04081/) (2022)
- [Can No-reference features help in Full-reference image quality estimation?](https://mlsanity.com/paper/2203.00845/) (2022)
- [No-Reference Image Contrast Assessment with Customized EfficientNet-B0](https://mlsanity.com/paper/2509.21967/) (2025)

## Abstract (arXiv)

Recently, deep convolutional neural networks (DCNN) that leverage the adversarial training framework for image restoration and enhancement have significantly improved the processed images' sharpness. Surprisingly, although these DCNNs produced crispier images than other methods visually, they may get a lower quality score when popular measures are employed for evaluating them. Therefore it is necessary to develop a quantitative metric to reflect their performances, which is well-aligned with the perceived quality of an image. Famous quantitative metrics such as Peak signal-to-noise ratio (PSNR), The structural similarity index measure (SSIM), and Perceptual Index (PI) are not well-correlated with the mean opinion score (MOS) for an image, especially for the neural networks trained with adversarial loss functions. This paper has proposed a convolutional neural network using an extension architecture of the traditional Siamese network so-called Siamese-Difference neural network. We have equipped this architecture with the spatial and channel-wise attention mechanism to increase our method's performance. Finally, we employed an auxiliary loss function to train our model. The suggested additional cost function surrogates ranking loss to increase Spearman's rank correlation coefficient while it is differentiable concerning the neural network parameters. Our method achieved superior performance in textbftextitNTIRE 2021 Perceptual Image Quality Assessment Challenge. The implementations of our proposed method are publicly available.